AI대학원 2021 가을 콜로퀴엄의 조경현 교수님(New York University) 강연을 안내드립니다.
관심 있는 분들의 많은 참석 바랍니다.
------- 이하 강연 정보 -------
일시/장소: 2021. 9. 24(금) 오전 10:00-11:10 / Zoom
제목: Machine learning, compression and Rissanen data analysis
연사: 조경현(Kyunghyun Cho), Professor, New York University
[사전 등록] https://bit.ly/PNUAI-Colloquium (사전 등록 시 Zoom URL을 보내드립니다)
In the first part of the talk, which serves as the background for the main part of the talk, I will draw a high-level illustration on how programming, data compression and machine learning (predictive modeling) are closely connected with each other. Once this connection is established, I will move on to the main part of the talk, in which I explain how this connection can be used for data analysis. In particular, I will focus on the aspect of analyzing the importance and necessity of features from the perspective of minimum dex-x-x-x-scription length by using its connection to Kolmogorov complexity. I will end the talk by illustrating how this way of data analysis allows us to investigate the importance of various features in widely used benchmark tasks, such as multi-hop question-answering, explainability of natural language inference and text classification. We refer this process by Rissanen data analysis, after late Jorma Rissanen who is considered the father of minimum dex-x-x-x-scription length principle.
Kyunghyun Cho is an associate professor of computer science and data science at New York University and CIFAR Fellow of Learning in Machines & Brains. He is also a senior director of frontier research at the Prescient Design team within Genentech Research & Early Development (gRED). He was a research scientist at Facebook AI Research from June 2017 to May 2020 and a postdoctoral fellow at University of Montreal until Summer 2015 under the supervision of Prof. Yoshua Bengio, after receiving PhD and MSc degrees from Aalto University April 2011 and April 2014, respectively, under the supervision of Prof. Juha Karhunen, Dr. Tapani Raiko and Dr. Alexander Ilin. He tries his best to find a balance among machine learning, natural language processing, and life, but almost always fails to do so.
* AI대학원 가을 콜로퀴엄에서는 매월 2회 AI분야 국내외 석학과 산업계 전문가를 초청하여
최근 AI연구동향과 AI융합 산업동향에 대한 강연을 듣고 있습니다. (하반기 강연 일정 : 하단 포스터)